Building maps
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 3.6.3
## -- Attaching packages ------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.3 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0
## Warning: package 'ggplot2' was built under R version 3.6.3
## Warning: package 'tibble' was built under R version 3.6.3
## Warning: package 'tidyr' was built under R version 3.6.3
## Warning: package 'purrr' was built under R version 3.6.3
## Warning: package 'dplyr' was built under R version 3.6.3
## -- Conflicts ---------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(maps)
## Warning: package 'maps' was built under R version 3.6.3
##
## Attaching package: 'maps'
## The following object is masked from 'package:purrr':
##
## map
library(mapdata)
## Warning: package 'mapdata' was built under R version 3.6.3
library(lubridate)
## Warning: package 'lubridate' was built under R version 3.6.3
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(viridis)
## Warning: package 'viridis' was built under R version 3.6.3
## Loading required package: viridisLite
## Warning: package 'viridisLite' was built under R version 3.6.3
library(wesanderson)
## Warning: package 'wesanderson' was built under R version 3.6.3
daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>%
rename(Long = "Long_")
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_character(),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character()
## )
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
borders("world", colour = NA, fill = "grey90") +
theme_bw() +
geom_point(shape = 21, color='blue', fill='blue', alpha = 0.5) +
labs(title = 'World COVID-19 confirmed cases',x = '', y = '',
size="Cases (x1000))") +
theme(legend.position = "right") +
coord_fixed(ratio=1.5)
## Warning: Removed 54 rows containing missing values (geom_point).
daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-05-2020.csv")) %>%
rename(Long = "Long_") %>%
filter(Country_Region == "US") %>%
filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
"Puerto Rico","Northern Mariana Islands",
"Virgin Islands", "Recovered", "Guam", "Grand Princess",
"District of Columbia", "Diamond Princess")) %>%
filter(Lat > 0)
## Parsed with column specification:
## cols(
## FIPS = col_character(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character()
## )
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed)) +
borders("state", colour = "black", fill = "grey90") +
theme_bw() +
geom_point(shape = 21, color='blue', fill='blue', alpha = 0.5) +
labs(title = 'COVID-19 confirmed cases in the United States', x = '', y = '',
size="Cases") +
theme(legend.position = "right") +
coord_fixed(ratio=1.5)
daily_report_2 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>%
rename(Long = "Long_") %>%
filter(Country_Region == "US") %>%
filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
"Puerto Rico","Northern Mariana Islands",
"Virgin Islands", "Recovered", "Guam", "Grand Princess",
"District of Columbia", "Diamond Princess")) %>%
filter(Lat > 0)
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report_2, aes(x = Long, y = Lat, size = Confirmed)) +
borders("state", colour = "white", fill = "grey90") +
geom_point(aes(x=Long, y=Lat, size=Confirmed, color=Confirmed),stroke=F, alpha=0.7) +
scale_size_continuous(name="Cases", range=c(1,7),
breaks=mybreaks, labels = c("1-99",
"100-999", "1,000-9,999", "10,000-99,999", "50,000+")) +
scale_color_viridis_c(option="viridis",name="Cases",
breaks=mybreaks, labels = c("1-99",
"100-999", "1,000-9,999", "10,000-99,999", "50,000+")) +
theme_void() +
guides( colour = guide_legend()) +
labs(title = "Anisa Dhana's lagout for COVID-19 confirmed cases in the United States") +
theme(
legend.position = "bottom",
text = element_text(color = "#22211d"),
plot.background = element_rect(fill = "#ffffff", color = NA),
panel.background = element_rect(fill = "#ffffff", color = NA),
legend.background = element_rect(fill = "#ffffff", color = NA)
) +
coord_fixed(ratio=1.5)
Mapping data to shapes
daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>%
rename(Long = "Long_") %>%
filter(Country_Region == "US") %>%
group_by(Province_State) %>%
summarize(Confirmed = sum(Confirmed)) %>%
mutate(Province_State = tolower(Province_State))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_character(),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
us <- map_data("state")
state_join <- left_join(us, daily_report, by = c("region" = "Province_State"))
Using R color palettes
ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) +
coord_fixed(1.3) +
geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
scale_fill_gradientn(colours =
wes_palette("GrandBudapest2", 100, type = "continuous"),
trans = "log10") +
labs(title = "COVID-19 confirmed cases in the United States")
library(RColorBrewer)
display.brewer.all(colorblindFriendly = TRUE)
report_09_26_2020 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>%
rename(Long = "Long_") %>%
unite(Key, Admin2, Province_State, sep = ".") %>%
group_by(Key) %>%
summarize(Confirmed = sum(Confirmed)) %>%
mutate(Key = tolower(Key))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
us <- map_data("state")
counties <- map_data("county") %>%
unite(Key, subregion, region, sep = ".", remove = FALSE)
state_join <- left_join(counties, report_09_26_2020, by = c("Key"))
ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) +
coord_fixed(1.3) +
borders("state", colour = "black") +
geom_polygon(data = state_join, aes(fill = Confirmed)) +
scale_fill_gradientn(colors = brewer.pal(n = 5, name = "PiYG"),
breaks = c(1, 10, 100, 1000, 10000, 100000),
trans = "log10", na.value = "White") +
ggtitle("Number of confirmed cases by US county") +
theme_grey()
## Warning: Transformation introduced infinite values in discrete y-axis
daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>%
rename(Long = "Long_") %>%
filter(Province_State == "Massachusetts") %>%
group_by(Admin2) %>%
summarize(Confirmed = sum(Confirmed)) %>%
mutate(Admin2 = tolower(Admin2))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_character(),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
us <- map_data("state")
ma_us <- subset(us, region == "massachusetts")
counties <- map_data("county")
ma_county <- subset(counties, region == "massachusetts")
ct_county <- subset(counties, region == "connecticut")
state_join <- left_join(ma_county, daily_report, by = c("subregion" = "Admin2"))
ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) +
coord_fixed(1.3) +
geom_polygon(data = state_join, aes(fill = Confirmed), color = "white") +
scale_fill_gradientn(colors = brewer.pal(n = 5, name = "RdPu"),
trans = "log10") +
labs(title = "COVID-19 confirmed cases in Massachusetts")
daily_report
## # A tibble: 14 x 2
## Admin2 Confirmed
## <chr> <dbl>
## 1 barnstable 283
## 2 berkshire 213
## 3 bristol 424
## 4 dukes and nantucket 12
## 5 essex 1039
## 6 franklin 85
## 7 hampden 546
## 8 hampshire 102
## 9 middlesex 1870
## 10 norfolk 938
## 11 plymouth 621
## 12 suffolk 1896
## 13 unassigned 270
## 14 worcester 667
Interactive graphs
library(plotly)
## Warning: package 'plotly' was built under R version 3.6.3
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
ggplotly(
ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) +
coord_fixed(1.3) +
geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
scale_fill_gradientn(colours =
wes_palette("Moonrise3", 100, type = "continuous")) +
ggtitle("COVID-19 cases in MA") +
labs(x=NULL, y=NULL) +
theme(panel.border = element_blank()) +
theme(panel.background = element_blank()) +
theme(axis.ticks = element_blank()) +
theme(axis.text = element_blank())
)
## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.
daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>%
rename(Long = "Long_") %>%
group_by(Country_Region) %>%
summarize(Confirmed = sum(Confirmed), Deaths = sum(Deaths)) %>%
filter("Lat" !="NA") %>%
filter("Long" !="NA")
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` ungrouping output (override with `.groups` argument)
world <- as_tibble(map_data("world"))
setdiff(world$region, daily_report$Country_Region)
## [1] "Aruba"
## [2] "Anguilla"
## [3] "American Samoa"
## [4] "Antarctica"
## [5] "French Southern and Antarctic Lands"
## [6] "Antigua"
## [7] "Barbuda"
## [8] "Saint Barthelemy"
## [9] "Bermuda"
## [10] "Ivory Coast"
## [11] "Democratic Republic of the Congo"
## [12] "Republic of Congo"
## [13] "Cook Islands"
## [14] "Cape Verde"
## [15] "Curacao"
## [16] "Cayman Islands"
## [17] "Czech Republic"
## [18] "Canary Islands"
## [19] "Falkland Islands"
## [20] "Reunion"
## [21] "Mayotte"
## [22] "French Guiana"
## [23] "Martinique"
## [24] "Guadeloupe"
## [25] "Faroe Islands"
## [26] "Micronesia"
## [27] "UK"
## [28] "Guernsey"
## [29] "Greenland"
## [30] "Guam"
## [31] "Heard Island"
## [32] "Isle of Man"
## [33] "Cocos Islands"
## [34] "Christmas Island"
## [35] "Chagos Archipelago"
## [36] "Jersey"
## [37] "Siachen Glacier"
## [38] "Kiribati"
## [39] "Nevis"
## [40] "Saint Kitts"
## [41] "South Korea"
## [42] "Saint Martin"
## [43] "Marshall Islands"
## [44] "Macedonia"
## [45] "Myanmar"
## [46] "Northern Mariana Islands"
## [47] "Montserrat"
## [48] "New Caledonia"
## [49] "Norfolk Island"
## [50] "Niue"
## [51] "Bonaire"
## [52] "Sint Eustatius"
## [53] "Saba"
## [54] "Nauru"
## [55] "Pitcairn Islands"
## [56] "Palau"
## [57] "Puerto Rico"
## [58] "North Korea"
## [59] "Madeira Islands"
## [60] "Azores"
## [61] "Palestine"
## [62] "French Polynesia"
## [63] "South Sandwich Islands"
## [64] "South Georgia"
## [65] "Saint Helena"
## [66] "Ascension Island"
## [67] "Solomon Islands"
## [68] "Saint Pierre and Miquelon"
## [69] "Swaziland"
## [70] "Sint Maarten"
## [71] "Turks and Caicos Islands"
## [72] "Turkmenistan"
## [73] "Tonga"
## [74] "Trinidad"
## [75] "Tobago"
## [76] "Taiwan"
## [77] "USA"
## [78] "Vatican"
## [79] "Grenadines"
## [80] "Saint Vincent"
## [81] "Virgin Islands"
## [82] "Vanuatu"
## [83] "Wallis and Futuna"
## [84] "Samoa"
world <- as_tibble(map_data("world")) %>%
mutate(region = str_replace_all(region, c("USA" = "US", "Czech Republic" = "Czechia", "Ivory Coast" = "Cote d'Ivoire", "Democratic Republic of the Congo" = "Congo (Kinshasa)", "Republic of Congo" = "Congo (Brazzaville)")))
country_join <- left_join(world, daily_report, by = c("region" = "Country_Region"))
ggplotly(
ggplot(data = world, mapping = aes(x = long, y = lat, text = region, group = group)) +
coord_fixed(1.3) +
geom_polygon(data = country_join, aes(fill = Deaths), color = "black") +
scale_fill_gradientn(colours = wes_palette("Royal2", 100, type = "continuous")) +
labs(title = "COVID-19 deaths")
)
Exercise 4
ggplotly(
ggplot(data = ct_county, mapping = aes(x = long, y = lat, group = group)) +
coord_fixed(1.3) +
geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
scale_fill_gradientn(colours =
wes_palette("Royal2", 100, type = "continuous")) +
ggtitle("COVID-19 cases in MA") +
labs(x=NULL, y=NULL) +
theme(panel.border = element_blank()) +
theme(panel.background = element_blank()) +
theme(axis.ticks = element_blank()) +
theme(axis.text = element_blank())
)